Keyphrases
- markov decision processes
- markov decision problems
- utility function
- average reward
- policy iteration
- markov decision process
- optimal policy
- reinforcement learning
- state space
- portfolio selection
- finite state
- infinite horizon
- stochastic games
- expected utility
- dynamic programming
- partially observable
- planning under uncertainty
- quasi linear
- linear programming
- least squares
- portfolio optimization
- decision processes
- action sets
- action space
- reinforcement learning algorithms
- average cost
- reward function
- decision theoretic
- dynamic programming algorithms
- queueing networks
- decision problems
- exploration strategy
- probability distribution
- learning algorithm